Path planning using sparse volumetric data

Abstract

A view of geometry captured in image data generated by an imaging sensor is compared with a description of the geometry in a volumetric data structure. The volumetric data structure describes the volume at a plurality of levels of detail and includes entries describing voxels defining subvolumes of the volume at multiple levels of detail. The volumetric data structure includes a first entry to describe voxels at a lowest one of the levels of detail and further includes a number of second entries to describe voxels at a higher, second level of detail, the voxels at the second level of detail representing subvolumes of the voxels at the first level of detail. Each of these entries include bits to indicate whether a corresponding one of the voxels is at least partially occupied with the geometry. One or more of these entries are used in the comparison with the image data.

The invention claimed is: 
     
       1. At least one non-transitory machine readable medium comprising instructions to cause at least one processor circuit to at least:
 access a voxel-based data structure representative of an environment, the voxel-based data structure based on light detection and ranging (LIDAR) data from multiple LIDAR sensors; 
 select elements of the voxel-based data structure based on occupancy associated with the elements; and 
 process the selected elements to determine navigation data for an autonomous vehicle. 
 
     
     
       2. The at least one non-transitory machine readable medium of  claim 1 , wherein the voxel-based data structure is associated with a map. 
     
     
       3. The at least one non-transitory machine readable medium of  claim 1 , wherein at least one of the LIDAR sensors is on a vehicle. 
     
     
       4. The at least one non-transitory machine readable medium of  claim 1 , wherein the instructions are to cause one or more of the at least one processor circuit to process at least one of the selected elements based on a convolutional neural network (CNN) to determine the navigation data. 
     
     
       5. The at least one non-transitory machine readable medium of  claim 1 , wherein the voxel-based data structure has a hierarchical arrangement. 
     
     
       6. The at least one non-transitory machine readable medium of  claim 5 , wherein a first hierarchical level of the voxel-based data structure is associated with a first level of detail, a second hierarchical level of the voxel-based data structure is associated with a second level of detail, and the second level of detail is different from the first level of detail. 
     
     
       7. The at least one non-transitory machine readable medium of  claim 1 , wherein the navigation data includes a starting position of the autonomous vehicle. 
     
     
       8. An apparatus comprising:
 interface circuitry; 
 machine readable instructions; and 
 at least one processor circuit to be programmed by the machine readable instructions to:
 access a voxel-based data structure representative of an environment, the voxel-based data structure based on light detection and ranging (LIDAR) data from multiple LIDAR sensors; 
 select elements of the voxel-based data structure based on occupancy associated with the elements; and 
 process the selected elements to determine navigation data. 
 
 
     
     
       9. The apparatus of  claim 8 , wherein the voxel-based data structure is associated with a map. 
     
     
       10. The apparatus of  claim 8 , wherein at least one of the LIDAR sensors is on a vehicle. 
     
     
       11. The apparatus of  claim 8 , wherein one or more of the at least one processor circuit is to process at least one of the selected elements based on a convolutional neural network (CNN) to determine the navigation data. 
     
     
       12. The apparatus of  claim 8 , wherein the voxel-based data structure is hierarchical. 
     
     
       13. The apparatus of  claim 12 , wherein a first level of the voxel-based data structure is associated with a first level of detail, a second level of the voxel-based data structure is associated with a second level of detail, and the second level of detail is different from the first level of detail. 
     
     
       14. The apparatus of  claim 8 , wherein the navigation data includes a starting orientation of an autonomous vehicle. 
     
     
       15. A method comprising:
 accessing a voxel-based data structure, the voxel-based data structure based on light detection and ranging (LIDAR) data representative of an environment; 
 selecting, by executing an instruction with at least one processor circuit, elements of the voxel-based data structure based on occupancy associated with the elements; and 
 processing the selected elements to determine navigation data; and 
 outputting the navigation data to an autonomous vehicle. 
 
     
     
       16. The method of  claim 15 , wherein the voxel-based data structure is associated with a map. 
     
     
       17. The method of  claim 15 , further including processing at least one of the selected elements based on a convolutional neural network (CNN) to determine the navigation data. 
     
     
       18. The method of  claim 15 , wherein the voxel-based data structure has a hierarchical structure. 
     
     
       19. The method of  claim 18 , wherein a first level of the voxel-based data structure is associated with a first level of detail, a second level of the voxel-based data structure is associated with a second level of detail, and the second level of detail is different from the first level of detail. 
     
     
       20. The method of  claim 15 , wherein the navigation data includes at least one of a position or an orientation of the autonomous vehicle.